mlsanityData to 7 Oct 2026

Path Aggregation Network for Instance Segmentation

arXiv 1803.01534 ↗First posted 5 Mar 2018cs.CVcited by 796

Not on the map. Why?

Abstract (arXiv)

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framework. Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature. We present adaptive feature pooling, which links feature grid and all feature levels to make useful information in each feature level propagate directly to following proposal subnetworks. A complementary branch capturing different views for each proposal is created to further improve mask prediction. These improvements are simple to implement, with subtle extra computational overhead. Our PANet reaches the 1st place in the COCO 2017 Challenge Instance Segmentation task and the 2nd place in Object Detection task without large-batch training. It is also state-of-the-art on MVD and Cityscapes. Code is available at https://github.com/ShuLiu1993/PANet

Key facts. Cited by 796 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 180; 2022: 179; 2023: 156; 2024: 116; 2025: 106; 2026: 59.

796 papers.

Sort:

By area:

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  3. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  4. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  5. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  6. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  7. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  8. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  10. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 300
  11. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  12. 2021Parametric Contrastive Learningcited by 217
38 more
  1. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
  2. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  3. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  4. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  5. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  6. 2023RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Modelcited by 180
  7. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  8. 2021Instances as Queriescited by 157
  9. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  10. 2023PolyFormer: Referring Image Segmentation as Sequential Polygon Generationcited by 147
  11. 2023DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Drivingcited by 142
  12. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  13. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  14. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  15. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
  16. 2021You Only Look One-level Featurecited by 116
  17. 2021Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentationcited by 111
  18. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 105
  19. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  20. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  21. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  22. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  23. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  24. 2022High-Quality Entity Segmentationcited by 93
  25. 2021CAT: Cross Attention in Vision Transformercited by 92
  26. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  27. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  28. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  29. 2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
  30. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82
  31. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  32. 2021Fourier Contour Embedding for Arbitrary-Shaped Text Detectioncited by 80
  33. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  34. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  35. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  36. 2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76
  37. 2021Large Scale Visual Food Recognitioncited by 75
  38. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74

50 most cited of 796 All 796 (JSON)